What are the hardware requirements for Qwen3.5 24.5B Reapped V1?

Qwen3.5 24.5B Reapped V1 requires approximately 50.1 GB of VRAM and supports a context window of 256K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 24.5B Reapped V1 and how large is it?

Qwen3.5 24.5B Reapped V1 is developed by groxaxo, a model with 25.1b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.5 24.5B Reapped V1?

Qwen3.5 24.5B Reapped V1 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 24.5B Reapped V1 by groxaxo — VRAM 50.1GB, 256K context

Name: Qwen3.5 24.5B Reapped V1
Author: groxaxo

Qwen3.5 24.5B Reapped V1 is an open-source language model by groxaxo. Features: 25.1b LLM, VRAM: 50.1GB, Context: 256K, License: apache-2.0, MoE, LLM Explorer Score: 0.27.

Agentic Coding Conversational En Endpoints compatible Lora Lora-merged Moe Pruned Qlora Qwen3 5 moe Qwen3 5 moe text Reap Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/groxaxo/Qwen3.5-24.5B-Reapped-v1

Qwen3.5 24.5B Reapped V1 Benchmarks

LLME Score: 0.26968

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

Qwen3.5 24.5B Reapped V1 (groxaxo/Qwen3.5-24.5B-Reapped-v1)

🌟 Advertise your project 🚀

Qwen3.5 24.5B Reapped V1 Parameters and Internals

LLM Name	Qwen3.5 24.5B Reapped V1
Repository 🤗	https://huggingface.co/groxaxo/Qwen3.5-24.5B-Reapped-v1
Model Size	25.1b
Required VRAM	50.1 GB
Updated	2026-06-26
Maintainer	groxaxo
Model Type	qwen3_5_moe_text
Model Files	4.9 GB: 1-of-11 4.8 GB: 2-of-11 4.8 GB: 3-of-11 4.8 GB: 4-of-11 4.8 GB: 5-of-11 4.8 GB: 6-of-11 4.8 GB: 7-of-11 4.8 GB: 8-of-11 4.8 GB: 9-of-11 4.8 GB: 10-of-11 2.0 GB: 11-of-11
Supported Languages	en
Model Architecture	Qwen3_5MoeForCausalLM
License	apache-2.0
Context Length	262144
Model Max Length	262144
Transformers Version	5.10.2
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	248320
LoRA Model	Yes
Errors	replace

Best Alternatives to Qwen3.5 24.5B Reapped V1

Best Alternatives	Context / RAM	Downloads	Likes
...n3.6 35B A3B Heretic REAP 0.30	256K / 50.2 GB	37	1

Note: green Score (e.g. "73.2") means that the model is better than groxaxo/Qwen3.5-24.5B-Reapped-v1.

Rank the Qwen3.5 24.5B Reapped V1 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

What open-source LLMs or SLMs are you in search of? 54565 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer

Qwen3.5 24.5B Reapped V1 by groxaxo

» All LLMs » groxaxo » Qwen3.5 24.5B Reapped V1 URL Share it on

Qwen3.5 24.5B Reapped V1 Benchmarks

Qwen3.5 24.5B Reapped V1 Parameters and Internals

Best Alternatives to Qwen3.5 24.5B Reapped V1

Rank the Qwen3.5 24.5B Reapped V1 Capabilities

What open-source LLMs or SLMs are you in search of? 54565 in total.